{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.13668383657932281, "min": 0.12329206615686417, "max": 1.4902220964431763, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4087.393310546875, "min": 3694.816650390625, "max": 45207.37890625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999958.0, "min": 29952.0, "max": 2999958.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999958.0, "min": 29952.0, "max": 2999958.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7825456857681274, "min": -0.11796242743730545, "max": 0.8589538931846619, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 233.1986083984375, "min": -28.31098175048828, "max": 263.564697265625, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.00839250348508358, "min": -0.03407864645123482, "max": 0.295978844165802, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.5009660720825195, "min": -10.053200721740723, "max": 71.03491973876953, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0686720154785906, "min": 0.06374061969031433, "max": 0.07583684972459673, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9614082167002684, "min": 0.4652735594728287, "max": 1.095566842200545, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014711982880336497, "min": 0.0006984896469204324, "max": 0.016890648094057624, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20596776032471095, "min": 0.009778855056886054, "max": 0.2533597214108644, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4689637960928575e-06, "min": 1.4689637960928575e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0565493145300004e-05, "min": 2.0565493145300004e-05, "max": 0.003969671076776333, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10048962142857143, "min": 0.10048962142857143, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4068547, "min": 1.3897045333333333, "max": 2.7232236666666667, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.891318071428572e-05, "min": 5.891318071428572e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008247845300000001, "min": 0.0008247845300000001, "max": 0.13233004429999998, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008021917194128036, "min": 0.00732433283701539, "max": 0.4307158291339874, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11230684071779251, "min": 0.10674920678138733, "max": 3.0150108337402344, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 225.2265625, "min": 212.28776978417267, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28829.0, "min": 15984.0, "max": 33420.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7591453009517863, "min": -1.0000000521540642, "max": 1.7877246309881625, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 225.17059852182865, "min": -32.000001668930054, "max": 246.70599907636642, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7591453009517863, "min": -1.0000000521540642, "max": 1.7877246309881625, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 225.17059852182865, "min": -32.000001668930054, "max": 246.70599907636642, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.01870430156054681, "min": 0.018180886194341304, "max": 8.79247400444001, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.3941505997499917, "min": 2.194988365925383, "max": 140.67958407104015, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1724831930", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1724842695" }, "total": 10765.686219158, "count": 1, "self": 0.6515384810008982, "children": { "run_training.setup": { "total": 0.06917175400030828, "count": 1, "self": 0.06917175400030828 }, "TrainerController.start_learning": { "total": 10764.965508923, "count": 1, "self": 7.355893671869126, "children": { "TrainerController._reset_env": { "total": 2.4122380089993385, "count": 1, "self": 2.4122380089993385 }, "TrainerController.advance": { "total": 10755.114327003132, "count": 194780, "self": 7.254484705539653, "children": { "env_step": { "total": 7458.566302713474, "count": 194780, "self": 6966.609177442762, "children": { "SubprocessEnvManager._take_step": { "total": 487.5966018033487, "count": 194780, "self": 20.33405268394381, "children": { "TorchPolicy.evaluate": { "total": 467.26254911940487, "count": 187557, "self": 467.26254911940487 } } }, "workers": { "total": 4.360523467363237, "count": 194780, "self": 0.0, "children": { "worker_root": { "total": 10742.091260657791, "count": 194780, "is_parallel": true, "self": 4327.2409730928075, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003177679000145872, "count": 1, "is_parallel": true, "self": 0.001074230000085663, "children": { "_process_rank_one_or_two_observation": { "total": 0.002103449000060209, "count": 8, "is_parallel": true, "self": 0.002103449000060209 } } }, "UnityEnvironment.step": { "total": 0.07774267199965834, "count": 1, "is_parallel": true, "self": 0.0010805679994518869, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005770469997514738, "count": 1, "is_parallel": true, "self": 0.0005770469997514738 }, "communicator.exchange": { "total": 0.0729205940006068, "count": 1, "is_parallel": true, "self": 0.0729205940006068 }, "steps_from_proto": { "total": 0.0031644629998481832, "count": 1, "is_parallel": true, "self": 0.0006591479996131966, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025053150002349867, "count": 8, "is_parallel": true, "self": 0.0025053150002349867 } } } } } } }, "UnityEnvironment.step": { "total": 6414.850287564984, "count": 194779, "is_parallel": true, "self": 145.2655434307526, "children": { "UnityEnvironment._generate_step_input": { "total": 87.76415363983597, "count": 194779, "is_parallel": true, "self": 87.76415363983597 }, "communicator.exchange": { "total": 5792.903103352046, "count": 194779, "is_parallel": true, "self": 5792.903103352046 }, "steps_from_proto": { "total": 388.9174871423493, "count": 194779, "is_parallel": true, "self": 84.32267455225065, "children": { "_process_rank_one_or_two_observation": { "total": 304.5948125900986, "count": 1558232, "is_parallel": true, "self": 304.5948125900986 } } } } } } } } } } }, "trainer_advance": { "total": 3289.2935395841187, "count": 194780, "self": 14.72361238916801, "children": { "process_trajectory": { "total": 513.9542409879823, "count": 194780, "self": 513.4184342059834, "children": { "RLTrainer._checkpoint": { "total": 0.5358067819988719, "count": 6, "self": 0.5358067819988719 } } }, "_update_policy": { "total": 2760.6156862069683, "count": 1396, "self": 1110.627917825791, "children": { "TorchPPOOptimizer.update": { "total": 1649.9877683811774, "count": 68391, "self": 1649.9877683811774 } } } } } } }, "trainer_threads": { "total": 1.0229996405541897e-06, "count": 1, "self": 1.0229996405541897e-06 }, "TrainerController._save_models": { "total": 0.08304921600029047, "count": 1, "self": 0.0020024340010422748, "children": { "RLTrainer._checkpoint": { "total": 0.0810467819992482, "count": 1, "self": 0.0810467819992482 } } } } } } }